Optimizer Benchmarking Needs to Account for Hyperparameter Tuning

25 Oct 2019Prabhu Teja SivaprasadFlorian MaiThijs VogelsMartin JaggiFrançois Fleuret

The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration. The efficacy of optimizers is often studied under near-optimal problem-specific hyperparameters, and finding these settings may be prohibitively costly for practitioners... (read more)

PDF Abstract


No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper